Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计提醒

qodo-get-relevant-rulesqodo 获取相关规则

Agent Skill

qodo-get-relevant-rules 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

727

周安装

30

GitHub Stars

30

下载量

238
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:qodo-get-relevant-rules(qodo 获取相关规则)
来源仓库:https://github.com/qodo-ai/qodo-skills
仓库路径:skills/qodo-get-relevant-rules
安装命令:
npx skills add https://github.com/qodo-ai/qodo-skills --skill qodo-get-relevant-rules
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/qodo-ai/qodo-skills --skill qodo-get-relevant-rules

简介

用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、任务场景或来源线索快速定位候选结果。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装。
  • 需确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • qodo-get-relevant-rules 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Get Qodo Relevant Rules Skill

Description

Searches for the most relevant Qodo coding rules for the current coding task. Instead of loading all rules, this skill generates a focused search query from the coding assignment and calls POST /rules/search to retrieve only the rules most relevant to the task at hand.

Use when you have a specific coding task and want targeted, ranked rules. This is the semantic-search alternative to qodo-get-rules.

Skip if "Qodo Rules Loaded" already appears in conversation context.


Workflow

Step 1: Check if Rules Already Loaded

If rules are already loaded (look for "Qodo Rules Loaded" in recent messages), skip to Step 6.

Step 2: Verify Working in a Git Repository

  • Check that the current directory is inside a git repository. If not, inform the user that a git repository is required and exit gracefully.

See repository scope detection for the git check command.

Step 3: Verify Qodo Configuration

Check that the required Qodo configuration is present. The default location is ~/.qodo/config.json.

  • API key: Read from ~/.qodo/config.json (API_KEY field). Environment variable QODO_API_KEY takes precedence. If not found, inform the user that an API key is required and provide setup instructions, then exit gracefully.
  • Environment name: Read from ~/.qodo/config.json (ENVIRONMENT_NAME field), with QODO_ENVIRONMENT_NAME environment variable taking precedence. If not found or empty, use production.
  • API URL override (optional): Read from ~/.qodo/config.json (QODO_API_URL field). If present, use {QODO_API_URL}/rules/v1 as the API base URL, ignoring ENVIRONMENT_NAME. If absent, the ENVIRONMENT_NAME-based URL is used.
  • Request ID: Generate a UUID (e.g. python3 -c "import uuid; print(uuid.uuid4())") to use as request-id for the API call.

Step 4: Generate Structured Search Queries from Coding Assignment

Generate two structured search queries that mirror the rule embedding format. The query quality directly determines retrieval quality.

Each query must use this exact three-line structure:

Name: {concise 5-10 word title of the rule this task would trigger}
Category: {one of: Security, Correctness, Quality, Reliability, Performance, Testability, Compliance, Accessibility, Observability, Architecture}
Content: {1-2 sentences describing what should be checked or enforced}

Query 1 (Topic query): Focused on the coding assignment's primary concern. Pick the most relevant Category and describe the specific check in Content. When the repository's tech stack is known, mention it in the Content field.

Query 2 (Cross-cutting query): Targets recurring quality and standards patterns that apply to most code changes. Choose Category based on the org's rule emphasis (Security, Compliance, Observability, or Architecture as default) — see query-generation.md for the full selection rules. Include concerns like module structure, type annotations, structured logging, and repository patterns in Content. Adjust Content to reflect the repository's tech stack when known.

This dual-query approach ensures retrieval of both topic-specific rules and cross-cutting quality rules that apply to nearly all code changes.

Do not generate queries in these formats -- they perform poorly with the embedding model:

  • Keyword list: authentication login JWT token Python FastAPI
  • Flat sentence: Adding a login authentication endpoint with JWT token credential validation

See query generation guidelines for the full strategy, category descriptions, and examples.

Step 5: Call POST /rules/search

Call the search endpoint once per query (topic query and cross-cutting query), each with top_k=20. Merge the results and deduplicate by rule ID, preserving the order from the topic query first, then filling from cross-cutting results. Cap the final merged list at 15-20 unique rules to avoid rule fatigue — if the combined set exceeds 20, truncate at 20, keeping topic results prioritized. When your tooling supports parallel execution (e.g., Claude Code parallel tool calls), run both calls in parallel to avoid added latency.

See search endpoint for the full request/response contract, top_k defaults, error handling, and API URL construction.

Step 6: Format and Output Rules

  • Print the "📋 Qodo Rules Loaded" header with the search query used and total rule count.
  • List rules in the order returned (they are already ranked by relevance):

- Each rule: - **{name}** [{severity}]: {content}

  • End output with ---.

Header format:

# 📋 Qodo Rules Loaded

Search query: `{SEARCH_QUERY}`
Rules loaded: **{TOTAL_RULES}** (ranked by relevance to your task)

These rules must be applied during code generation based on severity:

If no rules were returned, output:

# 📋 Qodo Rules Loaded

No relevant rules found for this task. Proceeding without rule constraints.

---

Do not crash or error — an empty result is valid.

Step 7: Apply Rules

Apply the returned rules to the coding task. Rules are returned ranked by relevance — apply all returned rules.

Inform the user about rule application after code generation:

  • Rules applied: List which rules were followed
  • No applicable rules: Inform: "No Qodo rules were applicable to this code change"

Configuration

See README.md for full configuration instructions, including API key setup and environment variable options.


Common Mistakes

  • Re-running when rules are loaded - Check for "Qodo Rules Loaded" in context first
  • Wrong query format - Write queries using the structured Name/Category/Content format, not keyword lists or flat sentences; the embedding model aligns best when the query mirrors the indexed structure
  • Single query only - Always generate both a topic query and a cross-cutting query; a single topic-focused query misses cross-cutting rules (architecture, quality, observability) that apply to most code changes
  • Vague query - The search query must capture the nature of the task; a generic Name or Content field returns irrelevant rules
  • Crashing on empty results - An empty rules list is valid; proceed without rule constraints
  • Not in git repo - Inform the user that a git repository is required and exit gracefully
  • No API key - Inform the user with setup instructions; set QODO_API_KEY or create ~/.qodo/config.json

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.36%
按下载量换算89

Claude

32.57%
按下载量换算78

Cursor

17.84%
按下载量换算42

Gemini CLI

9.27%
按下载量换算22

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills